ainewsblitz.com

Breaking

OpenAI reports Jalapeño inference chip leads commercial systems on efficiency

  • Infra & Chips

OpenAI says Jalapeño, its first custom inference chip, delivered 1.5× to 1.9× more AI work per watt than comparison systems at peak throughput, while reducing end-to-end latency by 1.7× to 3.6×. The company published its first measured results after testing the processor on SemiAnalysis’s public InferenceX benchmark.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,529 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year